Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

• URL: http://arxiv.org/abs/2603.14968v1
• Date: Mon, 16 Mar 2026 08:28:48 GMT
• Title: Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
• Abstract summary: TTP-Detect is a pioneering black-box framework designed for non-intrusive, third-party watermark verification.<n>It employs a proxy model to amplify watermark-relevant signals and a suite of complementary relative measurements to assess the alignment of the query text with watermarked distributions.<n>It achieves superior detection performance and robustness against diverse attacks.
• Score: 16.430415006488865
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verification. This dependency creates a fundamental barrier for real-world governance, as independent auditing becomes impossible without compromising model security or relying on the opaque claims of service providers. To resolve this dilemma, we introduce TTP-Detect, a pioneering black-box framework designed for non-intrusive, third-party watermark verification. By decoupling detection from injection, TTP-Detect reframes verification as a relative hypothesis testing problem. It employs a proxy model to amplify watermark-relevant signals and a suite of complementary relative measurements to assess the alignment of the query text with watermarked distributions. Extensive experiments across representative watermarking schemes, datasets and models demonstrate that TTP-Detect achieves superior detection performance and robustness against diverse attacks.

Related papers

• Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents [0.0]
  We study whether activation probes can detect credential access before output tokens are emitted.<n>Third, we treat multi-turn exfiltration as a cumulative information-flow problem.<n>Results suggest credential-exfiltration defenses should combine pre-output monitoring, canary detection, and temporal leakage accounting.
  arXiv  Detail & Related papers  (2026-06-02T18:53:17Z)
• Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought [22.88615312532184]
  BiCoT is a watermarking framework that embeds ownership signals into the internal geometry of reasoning traces.<n>To enable verification under model theft and representation drift, we introduce Robust Subspace Registration.<n> Experiments show that BiCoT preserves reasoning fidelity across diverse complex reasoning tasks.
  arXiv  Detail & Related papers  (2026-05-27T07:44:38Z)
• Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking [1.534847923698733]
  We present textbfBREW (Block-wise Reliable Embedding for Watermarking), a framework shifting the paradigm to emphdesignated verification.<n>Our framework is model-agnostic and theoretically grounded, providing a scalable solution for reliable forensic deployment.
  arXiv  Detail & Related papers  (2026-05-01T02:14:38Z)
• From Decoupled to Coupled: Robustness Verification for Learning-based Keypoint Detection with Joint Specifications [11.371752627865929]
  Keypoint detection underpins many vision tasks, including pose estimation, viewpoint recovery, and 3D reconstruction.<n>Despite its importance, formal robustness verification for keypoint detectors is largely unexplored due to high-dimensional inputs and continuous coordinate outputs.<n>We propose the first coupled robustness verification framework for heatmap-based keypoint detectors.
  arXiv  Detail & Related papers  (2026-03-05T19:01:53Z)
• Online LLM watermark detection via e-processes [3.0870861759929977]
  We develop a unified framework for watermark detection based on e-processes.<n>We propose various methods to construct empirically adaptive e-processes that can enhance the detection power.<n>Some experiments demonstrate that the proposed framework achieves competitive performance compared to existing watermark detection methods.
  arXiv  Detail & Related papers  (2026-02-15T19:37:06Z)
• Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text Detection [105.14032334647932]
  Machine-generated texts (MGTs) pose risks such as disinformation and phishing, highlighting the need for reliable detection.<n> Metric-based methods, which extract statistically distinguishable features of MGTs, are often more practical than complex model-based methods that are prone to overfitting.<n>We propose a Markov-informed score calibration strategy that models two relationships of context detection scores that may aid calibration.
  arXiv  Detail & Related papers  (2026-02-08T16:06:12Z)
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking [58.475471437150674]
  We propose sequential watermarking for soft prompts (SWAP)<n>SWAP encodes watermarks through a specific order of defender-specified out-of-distribution classes.<n>Experiments on 11 datasets demonstrate SWAP's effectiveness, harmlessness, and robustness against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-11-05T13:48:48Z)
• SSCL-BW: Sample-Specific Clean-Label Backdoor Watermarking for Dataset Ownership Verification [8.045712223215542]
  This paper proposes a sample-specific clean-label backdoor watermarking (i.e., SSCL-BW)<n>By training a U-Net-based watermarked sample generator, this method generates unique watermarks for each sample.<n>Experiments on benchmark datasets demonstrate the effectiveness of the proposed method and its robustness against potential watermark removal attacks.
  arXiv  Detail & Related papers  (2025-10-30T12:13:53Z)
• An Ensemble Framework for Unbiased Language Model Watermarking [60.99969104552168]
  We propose ENS, a novel ensemble framework that enhances the detectability and robustness of unbiased watermarks.<n>ENS sequentially composes multiple independent watermark instances, each governed by a distinct key, to amplify the watermark signal.<n> Empirical evaluations show that ENS substantially reduces the number of tokens needed for reliable detection and increases resistance to smoothing and paraphrasing attacks.
  arXiv  Detail & Related papers  (2025-09-28T19:37:44Z)
• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models [55.05404953041403]
  We propose a novel framework that seamlessly integrates a binary watermark into the diffusion generation process.<n>We show that StableGuard consistently outperforms state-of-the-art methods in image fidelity, watermark verification, and tampering localization.
  arXiv  Detail & Related papers  (2025-09-22T16:35:19Z)
• CertDW: Towards Certified Dataset Ownership Verification via Conformal Prediction [48.82467166657901]
  We propose the first certified dataset watermark (i.e., CertDW) and CertDW-based certified dataset ownership verification method.<n>Inspired by conformal prediction, we introduce two statistical measures, including principal probability (PP) and watermark robustness (WR)<n>We prove there exists a provable lower bound between PP and WR, enabling ownership verification when a suspicious model's WR value significantly exceeds the PP values of benign models trained on watermark-free datasets.
  arXiv  Detail & Related papers  (2025-06-16T07:17:23Z)
• CBW: Towards Dataset Ownership Verification for Speaker Verification via Clustering-based Backdoor Watermarking [85.68235482145091]
  Large-scale speech datasets have become valuable intellectual property.<n>We propose a novel dataset ownership verification method.<n>Our approach introduces a clustering-based backdoor watermark (CBW)<n>We conduct extensive experiments on benchmark datasets, verifying the effectiveness and robustness of our method against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-03-02T02:02:57Z)
• Black-Box Detection of Language Model Watermarks [1.9374282535132377]
  We develop rigorous statistical tests to detect, and estimate parameters, of all three popular watermarking scheme families.<n>We experimentally confirm the effectiveness of our methods on a range of schemes and a diverse set of open-source models.<n>Our findings indicate that current watermarking schemes are more detectable than previously believed.
  arXiv  Detail & Related papers  (2024-05-28T08:41:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.